Study identifies brain hemorrhage patients most likely to have treatable underlying condition

 | Post date: 2019/06/11 | 

When blood vessels in the brain rupture, or hemorrhage, and cause a stroke, large areas of the brain can be permanently damaged. Depending on the cause, some brain hemorrhages may hide underlying lesions that can be treated with surgery, embolization, radiation, or other treatments. Using MRI scans of patients diagnosed with intracerebral hemorrhage, clinical researchers at Jefferson have teased apart the groups most likely to have a treatable underlying condition.

The findings, published May 31st in the Journal of Neurosurgery, will help physicians determine which patients to send for immediate MRI and surgical treatment, and which should be treated with supportive care.

Intracerebral hemorrhage can be highly disabling and every attempt should be made to treat underlying lesions to prevent rebleeding. This study helps identify patients who have brain hemorrhages that are suspicious for underlying lesions and who should absolutely receive an MRI."

Neurosurgeon and senior author Pascal Jabbour, MD Professor of Neurological Surgery and the Chief of the Division of Neurovascular and Endovascular Neurosurgery at the Sidney Kimmel Medical College at Thomas Jefferson University

Together with first author and Neurosurgery Chief Resident Nohra Chalouhi, MD, the research team reviewed the records of 400 patients diagnosed with intracerebral hemorrhage at Jefferson. The researchers found that as many as 12.5 percent of patients carried underlying brain lesions, and further characterized the demographics of those patients so that physicians could rapidly identify suspicious hemorrhages.

They found that there was a clear demarcation of the types of hemorrhages. When bleeding occurred deep in the basal ganglia, only 5 percent of patients had treatable underlying lesions on MRI. When the bleeds occurred in the brainstem or on the outer surface of the brain, on the other hand, the chance of finding a lesion rose dramatically to 15-30 percent. Patients were also remarkably more likely to harbor lesions if they didn't also have hypertension.

The researchers also looked as age as a variable. "Patients over the age of 85 were very unlikely to have a treatable lesion," says Dr. Chalouhi. "Whereas in a patient who was younger than 50, the likelihood of finding a structural lesion as a cause of the hemorrhage was 37 percent."

The study found a large spectrum of lesions causing these hemorrhages. The most common of these were arteriovenous malformations, cavernous malformations, and brain tumors. Other causes included brain aneurysms, venous clots, and even brain abscesses or infections. These lesions were successfully treated at Jefferson Hospital for Neuroscience.

"For the first time, we have an algorithm for identifying patients with suspicious brain hemorrhages to undergo further testing and treatment," says Dr. Jabbour.


Thomas Jefferson University

Journal reference:

Jabbour, P. et al. (2019) Analysis of the utility of early MRI/MRA in 400 patients with spontaneous intracerebral hemorrhage. Journal of

View: 1785 Time(s)   |   Print: 154 Time(s)   |   Email: 0 Time(s)   |   0 Comment(s)

AI tool can aid in the diagnosis of brain aneurysms

 | Post date: 2019/06/11 | 

Doctors could soon get some help from an artificial intelligence tool when diagnosing brain aneurysms - bulges in blood vessels in the brain that can leak or burst open, potentially leading to stroke, brain damage or death.

The AI tool, developed by researchers at Stanford University and detailed in a paper published June 7 in JAMA Network Open, highlights areas of a brain scan that are likely to contain an aneurysm.

"There's been a lot of concern about how machine learning will actually work within the medical field," said Allison Park, a Stanford graduate student in statistics and co-lead author of the paper. "This research is an example of how humans stay involved in the diagnostic process, aided by an artificial intelligence tool."

This tool, which is built around an algorithm called HeadXNet, improved clinicians' ability to correctly identify aneurysms at a level equivalent to finding six more aneurysms in 100 scans that contain aneurysms. It also improved consensus among the interpreting clinicians. While the success of HeadXNet in these experiments is promising, the team of researchers - who have expertise in machine learning, radiology and neurosurgery - cautions that further investigation is needed to evaluate generalizability of the AI tool prior to real-time clinical deployment given differences in scanner hardware and imaging protocols across different hospital centers. The researchers plan to address such problems through multi-center collaboration.

Augmented expertise

Combing brain scans for signs of an aneurysm can mean scrolling through hundreds of images. Aneurysms come in many sizes and shapes and balloon out at tricky angles - some register as no more than a blip within the movie-like succession of images.

Search for an aneurysm is one of the most labor-intensive and critical tasks radiologists undertake. Given inherent challenges of complex neurovascular anatomy and potential fatal outcome of a missed aneurysm, it prompted me to apply advances in computer science and vision to neuroimaging."

Kristen Yeom, associate professor of radiology and co-senior author of the paper

Yeom brought the idea to the AI for Healthcare Bootcamp run by Stanford's Machine Learning Group, which is led by Andrew Ng, adjunct professor of computer science and co-senior author of the paper. The central challenge was creating an artificial intelligence tool that could accurately process these large stacks of 3D images and complement clinical diagnostic practice.

To train their algorithm, Yeom worked with Park and Christopher Chute, a graduate student in computer science, and outlined clinically significant aneurysms detectable on 611 computerized tomography (CT) angiogram head scans.

"We labelled, by hand, every voxel - the 3D equivalent to a pixel - with whether or not it was part of an aneurysm," said Chute, who is also co-lead author of the paper. "Building the training data was a pretty grueling task and there were a lot of data."

Following the training, the algorithm decides for each voxel of a scan whether there is an aneurysm present. The end result of the HeadXNet tool is the algorithm's conclusions overlaid as a semi-transparent highlight on top of the scan. This representation of the algorithm's decision makes it easy for the clinicians to still see what the scans look like without HeadXNet's input.

"We were interested how these scans with AI-added overlays would improve the performance of clinicians," said Pranav Rajpurkar, a graduate student in computer science and co-lead author of the paper. "Rather than just having the algorithm say that a scan contained an aneurysm, we were able to bring the exact locations of the aneurysms to the clinician's attention."

Eight clinicians tested HeadXNet by evaluating a set of 115 brain scans for aneurysm, once with the help of HeadXNet and once without. With the tool, the clinicians correctly identified more aneurysms, and therefore reduced the "miss" rate, and the clinicians were more likely to agree with one another. HeadXNet did not influence how long it took the clinicians to decide on a diagnosis or their ability to correctly identify scans without aneurysms - a guard against telling someone they have an aneurysm when they don't.

To other tasks and institutions

The machine learning methods at the heart of HeadXNet could likely be trained to identify other diseases inside and outside the brain. For example, Yeom imagines a future version could focus on speeding up identifying aneurysms after they have burst, saving precious time in an urgent situation. But a considerable hurdle remains in integrating any artificial intelligence medical tools with daily clinical workflow in radiology across hospitals.

Current scan viewers aren't designed to work with deep learning assistance, so the researchers had to custom-build tools to integrate HeadXNet within scan viewers. Similarly, variations in real-world data - as opposed to the data on which the algorithm is tested and trained - could reduce model performance. If the algorithm processes data from different kinds of scanners or imaging protocols, or a patient population that wasn't part of its original training, it might not work as expected.

"Because of these issues, I think deployment will come faster not with pure AI automation, but instead with AI and radiologists collaborating," said Ng. "We still have technical and non-technical work to do, but we as a community will get there and AI-radiologist collaboration is the most promising path."

View: 1789 Time(s)   |   Print: 157 Time(s)   |   Email: 0 Time(s)   |   0 Comment(s)

Alzheimer's could possibly be spread via contaminated neurosurgery

 | Post date: 2018/12/18 | 
Title: Alzheimer's could possibly be spread via contaminated neurosurgery
Researchers have found that surgical instruments used for neurosurgery could get contaminated by the altered brain proteins that are seen in Alzheimer’s disease. These instruments are capable of spreading the condition if not treated or decontaminated properly before reuse. The study results were published in the latest issue of the journal Nature.

View: 2801 Time(s)   |   Print: 234 Time(s)   |   Email: 0 Time(s)   |   0 Comment(s)

UCLA biologists uncover how head injuries can lead to serious brain disorders

 | Post date: 2018/11/21 | 
Title: UCLA biologists uncover how head injuries can lead to serious brain disorders
UCLA biologists have discovered how head injuries adversely affect individual cells and genes that can lead to serious brain disorders. The life scientists provide the first cell "atlas" of the hippocampus -- the part of the brain that helps regulate learning and memory -- when it is affected by traumatic brain injury. The team also proposes gene candidates for treating brain diseases associated with traumatic brain injury, such as Alzheimer's disease and post-traumatic stress disorder....

View: 2744 Time(s)   |   Print: 216 Time(s)   |   Email: 0 Time(s)   |   0 Comment(s)

NIH awards $3.5 million to continue development of robotic system for treating brain tumors

 | Post date: 2018/11/21 | 
Title: NIH awards $3.5 million to continue development of robotic system for treating brain tumors

Researchers at Worcester Polytechnic Institute (WPI) and Albany Medical College, along with corporate partners GE Global Research and Acoustic MedSystems Inc., have received a five-year, $3.5 million award from the National Institutes of Health (NIH) through the National Cancer Institutes' (NCI) Academic-Industrial Partnership program, to continue development of an innovative robotic system that, operating within an MRI scanner, can deliver a minimally invasive probe into the brain to destroy metastatic brain tumors with high-intensity therapeutic ultrasound under real-time guidance....

View: 2820 Time(s)   |   Print: 236 Time(s)   |   Email: 0 Time(s)   |   0 Comment(s)

New Penn Medicine Center offers hope in the fight against glioblastoma

 | Post date: 2018/11/5 | 

New Penn Medicine Center offers hope in the fight against glioblastoma

Today, Penn Medicine is announcing the newest Translational Center of Excellence (TCE) in the Abramson Cancer Center, focused on Glioblastoma Multiforme, the most common and lethal form of brain cancer. The team will investigate new immune therapies for glioblastoma and, in particular, design and test new CAR T cell therapies.....

Click Here


View: 2911 Time(s)   |   Print: 237 Time(s)   |   Email: 0 Time(s)   |   0 Comment(s)

FDA approves ultra-high-field 7T Terra MRI scanner for clinical use

 | Post date: 2018/11/5 | 

FDA approves ultra-high-field 7T Terra MRI scanner for clinical use
The ultra-high-field 7T Terra magnetic resonance imaging (MRI) scanner at the USC Mark and Mary Stevens Neuroimaging and Informatics Institute (INI) of the Keck School of Medicine of USC has received FDA approval for clinical use, opening up new avenues of care for patients with Alzheimer's disease, multiple sclerosis and other diseases that affect the brain. ....

Click Here

View: 2929 Time(s)   |   Print: 249 Time(s)   |   Email: 0 Time(s)   |   0 Comment(s)

The international and interim congress of Iranian neurosurgeons

 | Post date: 2018/08/19 | 
The international and interim congress of Iranian neurosurgeons

 3-5 OCT 2018

Babol University of Medical Sciences (BUMS)  

Website :

View: 3362 Time(s)   |   Print: 273 Time(s)   |   Email: 0 Time(s)   |   0 Comment(s)

Researchers study use of MRI-guided focused ultrasound to open blood-brain barrier

 | Post date: 2018/08/19 | 

Researchers study use of MRI-guided focused ultrasound to open blood-brain barrier

In the first such clinical trial in the United States, physician-scientists with the University of Maryland School of Medicine (UMSOM) are investigating the use of MRI-guided focused ultrasound to open the blood-brain barrier. The trial will be conducted with patients undergoing brain cancer surgery at the University of Maryland Medical Center (UMMC)....

View: 3247 Time(s)   |   Print: 257 Time(s)   |   Email: 0 Time(s)   |   0 Comment(s)

New 3D-printed device could help spinal cord injury patients regain some function

 | Post date: 2018/08/19 | 

New 3D-printed device could help spinal cord injury patients regain some function

Engineers and medical researchers at the University of Minnesota have teamed up to create a groundbreaking 3D-printed device that could someday help patients with long-term spinal cord injuries regain some function.....

View: 3213 Time(s)   |   Print: 239 Time(s)   |   Email: 0 Time(s)   |   0 Comment(s)

Virtual reality neurosurgery

 | Post date: 2018/07/31 | 
Healthcast: Virtual reality neurosurgery: A major hospital system is putting this familiar 3D technology into the hands of its pediatric neurosurgeons to help saves lives

SAN FRANCISCO, Calif. (Ivanhoe Newswire) - Most kids know all about virtual reality. It’s how they play video games and watch movies. But now a major hospital system is putting this familiar 3D technology into the hands of its pediatric neurosurgeons to help saves lives.

Mathias Hahn has always been the type of kid his mom would never have to worry about. Straight A’s, basketball, and cross country. But that all changed last fall.

“I woke up having a really bad headache,” Mathias told Ivanhoe.

It soon became clear to his mom that something more serious was happening.

Mathias’ mother, Lindsay Hahn, said, “The emergency room was able to do a CAT scan and they found the bleed.”

With a hemorrhage on his brain, Mathias was taken to the hospital where he began the fight for his life.

“He was lying in his ICU bed, paralyzed on one side and literally unable to say a word,” said Kurtis Auguste, MD, Pediatric Neurosurgeon at UCSF Benioff Children’s Hospital, Oakland.

“It was super scary. I didn’t know if I was going to be able to move again, maybe,” Mathias shared.

When Dr. Auguste began to operate to relieve pressure, he spotted a tumor.

“Where this was tucked underneath the edge of the bone, my visibility was limited and it was very difficult for me to reach and see,” he explained.

But this doctor let technology guide him. A virtual reality mapping system gave him a 360- degree view of Mathias’ brain constructed from CT and MRI images. It allowed Dr. Auguste to step inside Mathias’ brain and see the tumor from a new vantage point. He then shared his plan and headset with Mathias and his mom.

“It was comforting to see he had this tool that allowed him to see the tumor in so many different ways and decide how he could approach it safely,” Lindsay said.

Which is exactly what the doctor was able to do in surgery thanks to the VR technology. And as a result, Mathias is now healthy and cancer-free.

“I can just be a normal kid again,” Mathias said.

The virtual reality model provides surgeons a continuous guide to the intricate and crowded space inside our brains. UCSF Benioff Children’s Hospital in Oakland is among several institutions across the country to use this technology.

View: 3230 Time(s)   |   Print: 284 Time(s)   |   Email: 0 Time(s)   |   0 Comment(s)

Complication Avoidance and Management Techniques

 | Post date: 2018/07/31 | 

Book Review: Transsphenoidal Surgery: Complication Avoidance and Management Techniques

Deeper understanding and mastery of the techniques of transsphenoidal surgery is now essential for any practicing cranial neurosurgeon. As technology advances and our experience with this technique improve, many more surgical procedures for tumors in the skull base are best performed using this approach. The days when transsphenoidal surgery was limited to treatment of pituitary tumors is past, and therefore there is a need for comprehensive sources of information regarding all aspects of this surgical approach.

Advancements in the field have resulted from improved preoperative and intraoperative radiological imaging, enhanced microsurgical and endoscopic technology, refinements and delivery of focused radiosurgery via a variety of instruments, as well as a much more detailed and comprehensive understanding of tumor biology. The development of medical approaches based on an explosion of scientific knowledge regarding the molecular basis of tumor growth has also improved exponentially. All of this information is essential to understand before undertaking skull base surgery, and results from collegial interdisciplinary efforts. Today's cranial neurosurgeon has an obligation to understand these aspects of tumor biology and treatment in order to optimize his or her own delivery of patient care.

The anatomic complexities of the sellar and parasellar area as well as the entire skull base makes these areas one of the most challenging regions for delivering precise surgical intervention. As even the best devised surgical plans can fail, the successful surgeon needs to possess a detailed and comprehensive understanding of anatomy, surgical approaches, as well as complication recognition and avoidance.

This book edited by Drs Laws, Cohen-Gadol, Schwartz, and Sheehan provides a wealth of information regarding clinical knowledge and multidisciplinary approaches for management of patients harboring tumors that are suitable for this surgical approach. A number of chapters focus on surgical techniques, and emphasis is placed not only on the advantages or disadvantages of a particular approach, but also on methods to be utilized to avoid complications.

The book covers topics that range from the history of pituitary surgery and the transsphenoidal approach to quality of life assessments that are so important for patients. Chapters focus on preoperative assessment and planning, various intraoperative techniques, postoperative management, and adjuvant therapy for patients with recurrent or residual disease. A large number of chapters contain precise and detailed illustrations that leave the reader step-by-step through the various approaches that the authors are describing, and these are invaluable. Online videos associated with purchase of the book further enhance one's ability to study these techniques in detail. The diversity of topics in the book also underscores the multidisciplinary team approach that is essential for management of patient's with these conditions.


Every chapter is written by a well-known and established expert in the field. Many of these contributors share “pearls” of wisdom that has been gained over many decades of clinical experience. Variations in technique from one expert to another exist, and the astute reader has an opportunity to evaluate each aspect of these various techniques and decide which will be best to utilize in different clinical situations.

Like any book, some chapters are better than others and contain more detailed diagrams and illustrations. Chapters regarding the surgical anatomy of the sellar region, combined hybrid microscopic and endoscopic transsphenoidal surgery, transcranial approaches to the sellar and parasellar areas, and the role of endoscopic transsphenoidal surgery in the management of complex lesions involving the skull base are particularly helpful because of extensive diagrams and illustrations that very accurately and precisely demonstrate the anatomy and the step-by-step details of the various surgical approaches. Other chapters regarding medical management of pituitary adenoma patients, transsphenoidal surgery for recurrent disease, and surgical treatment of craniopharyngiomas are also very useful and provide new and important information.

Chapters discussing detailed information and outcome data for patients with prolactinomas, growth hormone tumors, and Cushing's disease provide new data regarding the outcome of surgical intervention. Chapters discussing pituitary apoplexy and the treatment of pituitary tumors in pediatric patients, as well as the approach giant adenomas are also very useful. Information regarding stereotactic radiosurgery and operative indications and pitfalls also are useful. The chapter on the neuro-ophthalmology of patients with these conditions is particularly detailed and useful for surgeons who treat patients with disorders in the visual system. The online extras in the form of video demonstrations represent hundreds of hours of work by the various authors, and are a wonderful enhancement for those who purchase the book.

The book is a useful addition to the library of all surgeons who deal with skull base cranial surgery, and provides outstanding information and reference sources for complex skull base procedures amenable to the transsphenoidal approach. As technology advances and outcomes using this technique continue to be superior, more cranial surgeons should familiarize themselves with this technique.

View: 3097 Time(s)   |   Print: 264 Time(s)   |   Email: 0 Time(s)   |   0 Comment(s)

© 2020 All Rights Reserved | Iranian Journal of Neurosurgery

Designed & Developed by : Yektaweb